A high-integrity debugging framework for AI agents that enforces a root-cause-first approach to eliminate symptom-only fixes.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gstack-openclaw-investigate
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install gstack-openclaw-investigate using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
This skill implements a rigorous four-phase debugging protocol designed to prevent the common pitfall of fixing symptoms rather than underlying issues. By adhering to the Iron Law—no fixes without a proven root cause—it ensures that AI agents provide long-term stability rather than temporary patches that make future bugs harder to find. It is a vital addition to the Openclaw Skills library for any developer focused on maintainable code.
Integrated into the broader Openclaw Skills ecosystem, this skill leverages git history, pattern analysis, and empirical hypothesis testing to systematically dismantle complex software errors. It transforms the debugging process from a series of guesses into a repeatable, scientific workflow that results in documented, verifiable solutions.
To integrate this skill into your agent's workflow, ensure the skill definition is accessible in your project's configuration directory.
# Example of adding the skill to your local environment
mkdir -p .openclaw/skills
cp gstack-openclaw-investigate.md .openclaw/skills/
Once installed, the agent will proactively trigger these phases when tasked with debugging or error resolution.
The skill produces a structured Debug Report saved to the project's memory system to ensure context persistence.
| Feature | Description |
|---|---|
| Symptom | Clear description of the error or unexpected behavior observed by the user. |
| Root Cause | The specific, validated reason why the failure occurred. |
| Fix | File references and the minimal diff applied to resolve the issue. |
| Evidence | Test output or reproduction logs showing the fix works. |
| Storage Path | Reports are saved to memory/YYYY-MM-DD-debug-report.md. |
Loading
An advanced git analysis tool that generates comprehensive weekly engineering retrospectives with team-aware metrics and trend tracking.

A sophisticated emotional intelligence layer that provides permanent memory and cross-agent experience sharing for your AI ecosystem.

A strategic AI skill that applies Lei Jun's five core mental models to evaluate products, business trends, and operational efficiency.

An automated engine that produces ranked improvement candidates for AI skills based on feedback loops, failure traces, and target analysis.

A powerful automation tool to synchronize local AI agent skills with GitHub repositories for versioning, sharing, and secure backup.

An automated research agent that synthesizes technical humanoid-robot papers into professional Chinese briefs focused on industrial design and product definition.








































